Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 96 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 6.2807. Min Range: -6.2807

Max Act: 6.2807. Min Act: -0.1700

Data Index: 8348882 (Open Web Text)

Max Activating Token Index: 646

Text #1

Max Range: 6.2807. Min Range: -6.2807

Max Act: 6.0698. Min Act: -0.1700

Data Index: 4980533 (Open Web Text)

Max Activating Token Index: 915

Text #2

Max Range: 6.2807. Min Range: -6.2807

Max Act: 6.0089. Min Act: -0.1700

Data Index: 839265 (Open Web Text)

Max Activating Token Index: 629

Text #3

Max Range: 6.2807. Min Range: -6.2807

Max Act: 6.0229. Min Act: -0.1700

Data Index: 6660641 (Open Web Text)

Max Activating Token Index: 171

Text #4

Max Range: 6.2807. Min Range: -6.2807

Max Act: 6.0091. Min Act: -0.1700

Data Index: 2820774 (Open Web Text)

Max Activating Token Index: 254

Text #5

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9564. Min Act: -0.1700

Data Index: 4515444 (Open Web Text)

Max Activating Token Index: 488

Text #6

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9790. Min Act: -0.1700

Data Index: 6552504 (Open Web Text)

Max Activating Token Index: 766

Text #7

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9934. Min Act: -0.1700

Data Index: 7737453 (Open Web Text)

Max Activating Token Index: 815

Text #8

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9554. Min Act: -0.1700

Data Index: 2402922 (Open Web Text)

Max Activating Token Index: 138

Text #9

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9175. Min Act: -0.1700

Data Index: 1321762 (Open Web Text)

Max Activating Token Index: 791

Text #10

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.8931. Min Act: -0.1700

Data Index: 2746331 (Open Web Text)

Max Activating Token Index: 873

Text #11

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9432. Min Act: -0.1700

Data Index: 3886127 (Open Web Text)

Max Activating Token Index: 175

Text #12

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9129. Min Act: -0.1700

Data Index: 6600915 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9189. Min Act: -0.1700

Data Index: 1127139 (Open Web Text)

Max Activating Token Index: 604

Text #14

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9275. Min Act: -0.1700

Data Index: 1245582 (Open Web Text)

Max Activating Token Index: 693

Text #15

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9216. Min Act: -0.1700

Data Index: 1547778 (Open Web Text)

Max Activating Token Index: 255

Text #16

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.9318. Min Act: -0.1700

Data Index: 1861157 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.8969. Min Act: -0.1700

Data Index: 5524230 (Open Web Text)

Max Activating Token Index: 886

Text #18

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.8897. Min Act: -0.1700

Data Index: 4585228 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 6.2807. Min Range: -6.2807

Max Act: 5.8757. Min Act: -0.1700

Data Index: 4659396 (Open Web Text)

Max Activating Token Index: 436